XIMEA and the Swiss Federal Institute of Technology used high-speed cameras to discover the winner of the final challenge between humans and robots – table foosball!
Professors and students at the Swiss Federal Institute of Technology in Lausanne they developed a robot player installed on a foosball table, which can be more accurate, faster and can formulate better strategies than any other human player.
The idea is to replace human players with a system capable of sensing the position of the ball on the table, evaluating a strategy to score and commanding the player’s commands using precision motors to execute this strategy.
The latest improvement in vision and strategy performance refers to the robot’s ability to keep the position of the ball under control, possible by implementing a XIMEA xiQ high-speed camera.
The camera, positioned under the table, runs at 500 frames per second and creates a solid base for detecting the ball in real time. In the current stage of development, the foosball robot can defeat any ordinary player it meets.
How did they build the robot that defeats you in foosball?
The Automatic Control Baby-foot project is one of several projects at EPFL (École polytechnique fédérale de Lausanne).
The entire audience is fascinated by the concept and implementation every time it is exposed, thanks to the ingenious way the lab has worked to bring an old game to 21st century technology.
At first glance, the foosball table in the middle of the Auto Control Lab looks perfectly normal. However, the appearance can be misleading.
One of the levers has a mechanical arm capable of propelling the ball into the opponent’s goal at a speed of six meters per second.
“This is already enough to defeat the average player,” said researcher Christophe Salzmann, who is leading the project. And this is only the beginning.
Among many other disciplines, this project requires knowledge of mechanics, analog and digital electronics and programming.
Full automation of the rotating arm needs to be improved to implement complex calculations during the game. That is, not only defensive strategies, but also the attack and early evaluation of opponents’ movements, as a goal of the project.
The general purpose is to provide the automated laboratory with a concrete, efficient and functional demonstration system for both software and hardware assemblies.